© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2345
    Prev
    Next
    INDEX
    Explanations

    Cauchy, central limit, Le Chatelier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ofile
    -0.09
    stu
    -0.09
    ezz
    -0.08
    زÙĩ
    -0.08
    mts
    -0.08
    nts
    -0.08
    åĽ¾çīĩæĿ¥æºIJäºİç½ij绾
    -0.08
    asel
    -0.08
    IDEO
    -0.08
    .jms
    -0.08
    POSITIVE LOGITS
    0.07
    l
    0.07
    ic
    0.07
    i
    0.06
    R
    0.06
    -
    0.06
     applied
    0.06
    Extended
    0.06
    بار
    0.06
    ian
    0.06
    Activations Density 0.014%

    No Known Activations